- Kao, J.-Y., Tian, D., Mansour, H., Ortega, A., Vetro, A., "Disc-Glasso: Discriminative Graph Learning with Sparsity Regularization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-018 PDF- @inproceedings{Kao2017mar,
- author = {Kao, Jiun-Yu and Tian, Dong and Mansour, Hassan and Ortega, Antonio and Vetro, Anthony},
- title = {{Disc-Glasso: Discriminative Graph Learning with Sparsity Regularization}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-018}
- }
- Kim, S., Hori, T., Watanabe, S., "Joint CTC- Attention Based End-to-End Speech Recognition Using Multi-task Learning", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-016 PDF Video- @inproceedings{Kim2017mar,
- author = {Kim, Suyoun and Hori, Takaaki and Watanabe, Shinji},
- title = {{Joint CTC- Attention Based End-to-End Speech Recognition Using Multi-task Learning}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-016}
- }
- Li, Q., Liu, S., Mansour, H., Wakin, M., Yang, D., Zhu, Z., "Jazz: A Companion to Music for Frequency Estimation with Missing Data", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-013 PDF- @inproceedings{Li2017mar,
- author = {Li, Qiuwei and Liu, Shuang and Mansour, Hassan and Wakin, Michael and Yang, Dehui and Zhu, Zhihui},
- title = {{Jazz: A Companion to Music for Frequency Estimation with Missing Data}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-013}
- }
- Liu, H.-Y., Kamilov, U., Liu, D., Mansour, H., Boufounos, P.T., "Compressive Imaging with Iterative Forward Models", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-009 PDF- @inproceedings{Liu2017mar2,
- author = {Liu, Hsiou-Yuan and Kamilov, Ulugbek and Liu, Dehong and Mansour, Hassan and Boufounos, Petros T.},
- title = {{Compressive Imaging with Iterative Forward Models}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-009}
- }
- Luo, Y., Chen, Z., Hershey, J.R., Le Roux, J., Mesgarani, N., "Deep Clustering and Conventional Networks for Music Separation: Strong Together", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-010 PDF- @inproceedings{Luo2017mar,
- author = {Luo, Yi and Chen, Zhuo and Hershey, John R. and {Le Roux}, Jonathan and Mesgarani, Nima},
- title = {{Deep Clustering and Conventional Networks for Music Separation: Strong Together}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-010}
- }
- Meng, Z., Watanabe, S., Hershey, J.R., Erdogan, H., "Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-012 PDF- @inproceedings{Meng2017mar,
- author = {Meng, Zhong and Watanabe, Shinji and Hershey, John R. and Erdogan, Hakan},
- title = {{Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-012}
- }
- Wang, Y., Raval, N.J., Ishwar, P., Hattori, M., Hirano, T., Matsuda, N., Shimizu, R., "On Methods for Privacy-Preserving Energy Disaggregation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-015 PDF- @inproceedings{Wang2017mar2,
- author = {Wang, Ye and Raval, Nisarg J and Ishwar, Prakash and Hattori, Mitsuhiro and Hirano, Takato and Matsuda, Nori and Shimizu, Rina},
- title = {{On Methods for Privacy-Preserving Energy Disaggregation}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-015}
- }
- Watanabe, S., Hori, T., Le Roux, J., Hershey, J.R., "Student-Teacher Network Learning with Enhanced Features", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-011 PDF- @inproceedings{Watanabe2017mar,
- author = {Watanabe, Shinji and Hori, Takaaki and {Le Roux}, Jonathan and Hershey, John R.},
- title = {{Student- Teacher Network Learning with Enhanced Features}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-011}
- }
- Xiao, X., Watanabe, S., Chng, E.S., Li, H., "Beamforming Networks Using Spatial Covariance Features for Far-field Speech Recognition", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)<br />
, DOI: 10.1109/APSIPA.2016.7820724, December 2016.
BibTeX TR2016-162 PDF- @inproceedings{Xiao2016dec,
- author = {Xiao, Xiong and Watanabe, Shinji and Chng, Eng Siong and Li, Haizhou},
- title = {{Beamforming Networks Using Spatial Covariance Features for Far-field Speech Recognition}},
- booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
}, - year = 2016,
- month = dec,
- doi = {10.1109/APSIPA.2016.7820724},
- url = {https://www.merl.com/publications/TR2016-162}
- }
- Takano, T., Moriya, T., Shinozaki, T., Watanabe, S., Hori, T., Duh, K., "Automated Structure Discovery and Parameter Tuning of Neural Network Language Model Based on Evolution Strategy", IEEE Spoken Language Technology Workshop (SLT), DOI: 10.1109/SLT.2016.7846334, December 2016.
BibTeX TR2016-173 PDF- @inproceedings{Takano2016dec,
- author = {Takano, Tomihiro and Moriya, Takafumi and Shinozaki, Takahiro and Watanabe, Shinji and Hori, Takaaki and Duh, Kevin},
- title = {{Automated Structure Discovery and Parameter Tuning of Neural Network Language Model Based on Evolution Strategy}},
- booktitle = {IEEE Spoken Language Technology Workshop (SLT)},
- year = 2016,
- month = dec,
- doi = {10.1109/SLT.2016.7846334},
- url = {https://www.merl.com/publications/TR2016-173}
- }
- Barker, J., Marxer, R., Vincent, E., Watanabe, S., "The Third 'CHIME' Speech Separation and Recognition Challenge: Analysis and Outcomes", Computer Speech & Language, DOI: 10.1016/j.csl.2016.10.005, December 2016.
BibTeX TR2016-171 PDF- @article{Barker2016dec,
- author = {Barker, Jon and Marxer, Ricard and Vincent, Emmanuel and Watanabe, Shinji},
- title = {{The Third 'CHIME' Speech Separation and Recognition Challenge: Analysis and Outcomes}},
- journal = {Computer Speech \& Language},
- year = 2016,
- month = dec,
- publisher = {Elsevier},
- doi = {10.1016/j.csl.2016.10.005},
- url = {https://www.merl.com/publications/TR2016-171}
- }
- Vincent, E., Watanabe, S., Nugraha, A.A., Barker, J., Marxer, R., "An analysis of environment, microphone and data simulation mismatches in robust speech recognition", Computer Speech & Language, DOI: 10.1016/j.csl.2016.11.005, December 2016.
BibTeX TR2016-172 PDF- @article{Vincent2016dec,
- author = {Vincent, Emmanuel and Watanabe, Shinji and Nugraha, Aditya Arie and Barker, Jon and Marxer, Ricard},
- title = {{An analysis of environment, microphone and data simulation mismatches in robust speech recognition}},
- journal = {Computer Speech \& Language},
- year = 2016,
- month = dec,
- publisher = {Elsevier},
- doi = {10.1016/j.csl.2016.11.005},
- url = {https://www.merl.com/publications/TR2016-172}
- }
- Delcroix, M., Watanabe, S., "Recent Advances in Distant Speech Recognition," Tech. Rep. TR2016-115, Interspeech Tutorials, September 2016.
BibTeX TR2016-115 PDF- @techreport{Delcroix2016sep,
- author = {Delcroix, Marc and Watanabe, Shinji},
- title = {{Recent Advances in Distant Speech Recognition}},
- booktitle = {Interspeech Tutorials},
- institution = {Interspeech},
- year = 2016,
- month = sep,
- url = {https://www.merl.com/publications/TR2016-115}
- }
- Le Roux, J., Vincent, E., Erdogan, H., "Learning-Based Approaches to Speech Enhancement and Separation," Tech. Rep. TR2016-113, Interspeech Tutorials, September 2016.
BibTeX TR2016-113 PDF- @techreport{LeRoux2016sep,
- author = {{Le Roux}, Jonathan and Vincent, Emmanuel and Erdogan, Hakan},
- title = {{Learning- Based Approaches to Speech Enhancement and Separation}},
- booktitle = {Interspeech Tutorials},
- year = 2016,
- month = sep,
- url = {https://www.merl.com/publications/TR2016-113}
- }
- Erdogan, H., Hershey, J.R., Watanabe, S., Mandel, M., Le Roux, J., "Improved MVDR beamforming using single-channel mask prediction networks", Interspeech, DOI: 10.21437/Interspeech.2016-552, September 2016, pp. 1981-1985.
BibTeX TR2016-072 PDF- @inproceedings{Erdogan2016sep,
- author = {Erdogan, Hakan and Hershey, John R. and Watanabe, Shinji and Mandel, Michael and {Le Roux}, Jonathan},
- title = {{Improved MVDR beamforming using single-channel mask prediction networks}},
- booktitle = {Interspeech},
- year = 2016,
- pages = {1981--1985},
- month = sep,
- doi = {10.21437/Interspeech.2016-552},
- url = {https://www.merl.com/publications/TR2016-072}
- }
- Isik, Y., Le Roux, J., Chen, Z., Watanabe, S., Hershey, J.R., "Single-Channel Multi-Speaker Separation using Deep Clustering", Interspeech, DOI: 10.21437/Interspeech.2016-1176, September 2016, pp. 545-549.
BibTeX TR2016-073 PDF- @inproceedings{Isik2016sep,
- author = {Isik, Yusuf and {Le Roux}, Jonathan and Chen, Zhuo and Watanabe, Shinji and Hershey, John R.},
- title = {{Single-Channel Multi-Speaker Separation using Deep Clustering}},
- booktitle = {Interspeech},
- year = 2016,
- pages = {545--549},
- month = sep,
- doi = {10.21437/Interspeech.2016-1176},
- url = {https://www.merl.com/publications/TR2016-073}
- }
- Zmolikova, K., Karafiat, M., Vesely, K., Delcroix, M., Watanabe, S., Burget, L., Cernocky, J.H., "Data selection by sequence summarizing neural network in mismatch condition training", Interspeech, DOI: 10.21437/Interspeech.2016-741, September 2016, pp. 2354-2358.
BibTeX TR2016-075 PDF- @inproceedings{Zmolikova2016sep,
- author = {Zmolikova, Katerina and Karafiat, Martin and Vesely, Karel and Delcroix, Marc and Watanabe, Shinji and Burget, Lukas and Cernocky, Jan, Honza},
- title = {{Data selection by sequence summarizing neural network in mismatch condition training}},
- booktitle = {Interspeech},
- year = 2016,
- pages = {2354--2358},
- month = sep,
- doi = {10.21437/Interspeech.2016-741},
- url = {https://www.merl.com/publications/TR2016-075}
- }
- Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J., Takeda, K., "Bidirectional LSTM-HMM Hybrid System for Polyphonic Sound Event Detection", Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), September 2016, pp. 35-39.
BibTeX TR2016-114 PDF- @inproceedings{Hayashi2016sep,
- author = {Hayashi, Tomoki and Watanabe, Shinji and Toda, Tomoki and Hori, Takaaki and {Le Roux}, Jonathan and Takeda, Kazuya},
- title = {{Bidirectional LSTM-HMM Hybrid System for Polyphonic Sound Event Detection}},
- booktitle = {Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)},
- year = 2016,
- pages = {35--39},
- month = sep,
- url = {https://www.merl.com/publications/TR2016-114}
- }
- Castorena, J., Kamilov, U., Boufounos, P.T., "Autocalibration of LIDAR and Optical Cameras via Edge Alignment", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7472200, March 2016, pp. 2862-2866.
BibTeX TR2016-009 PDF- @inproceedings{Castorena2016mar,
- author = {Castorena, Juan and Kamilov, Ulugbek and Boufounos, Petros T.},
- title = {{Autocalibration of LIDAR and Optical Cameras via Edge Alignment}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {2862--2866},
- month = mar,
- doi = {10.1109/ICASSP.2016.7472200},
- url = {https://www.merl.com/publications/TR2016-009}
- }
- Hershey, J.R., Chen, Z., Le Roux, J., Watanabe, S., "Deep Clustering: Discriminative Embeddings for Segmentation and Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7471631, March 2016, pp. 31-35.
BibTeX TR2016-003 PDF- @inproceedings{Hershey2016mar,
- author = {Hershey, John R. and Chen, Zhuo and {Le Roux}, Jonathan and Watanabe, Shinji},
- title = {{Deep Clustering: Discriminative Embeddings for Segmentation and Separation}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {31--35},
- month = mar,
- doi = {10.1109/ICASSP.2016.7471631},
- url = {https://www.merl.com/publications/TR2016-003}
- }
- Hori, T., Hori, C., Watanabe, S., Hershey, J.R., "Minimum Word Error Training of Long Short-Term Memory Recurrent Neural Network Language Models for Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7472827, March 2016, pp. 5990-5994.
BibTeX TR2016-011 PDF- @inproceedings{Hori2016mar,
- author = {Hori, Takaaki and Hori, Chiori and Watanabe, Shinji and Hershey, John R.},
- title = {{Minimum Word Error Training of Long Short-Term Memory Recurrent Neural Network Language Models for Speech Recognition}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {5990--5994},
- month = mar,
- doi = {10.1109/ICASSP.2016.7472827},
- url = {https://www.merl.com/publications/TR2016-011}
- }
- Kamilov, U., "Parallel Proximal Methods for Total Variation Minimization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.74772568, March 2016, pp. 4697-4701.
BibTeX TR2016-007 PDF- @inproceedings{Kamilov2016mar1,
- author = {Kamilov, Ulugbek},
- title = {{Parallel Proximal Methods for Total Variation Minimization}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {4697--4701},
- month = mar,
- doi = {10.1109/ICASSP.2016.74772568},
- url = {https://www.merl.com/publications/TR2016-007}
- }
- Kao, J.-Y., Tian, D., Mansour, H., Ortega, A., Vetro, A., "Geometric-Guided Label Propagation for Moving Object Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.747933, March 2016, pp. 1531-1535.
BibTeX TR2016-005 PDF- @inproceedings{Kao2016mar,
- author = {Kao, Jiun-Yu and Tian, Dong and Mansour, Hassan and Ortega, Antonio and Vetro, Anthony},
- title = {{Geometric-Guided Label Propagation for Moving Object Detection}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {1531--1535},
- month = mar,
- doi = {10.1109/ICASSP.2016.747933},
- url = {https://www.merl.com/publications/TR2016-005}
- }
- Mansour, H., Kamilov, U., "Multipath Removal by Online Blind Deconvolution in Through-the-Wall-Imaging", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7472249, March 2016, pp. 3106-3110.
BibTeX TR2016-006 PDF- @inproceedings{Mansour2016mar1,
- author = {Mansour, Hassan and Kamilov, Ulugbek},
- title = {{Multipath Removal by Online Blind Deconvolution in Through-the-Wall-Imaging}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {3106--3110},
- month = mar,
- doi = {10.1109/ICASSP.2016.7472249},
- url = {https://www.merl.com/publications/TR2016-006}
- }
- Suryaprakash, R.T., Pajovic, M., Kim, K.J., Orlik, P.V., "Millimeter Wave Communications Channel Estimation via Bayesian Group Sparse Recovery", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7472309, March 2016, pp. 3406-3410.
BibTeX TR2016-012 PDF- @inproceedings{Suryaprakash2016mar,
- author = {Suryaprakash, Raj Tejas and Pajovic, Milutin and Kim, Kyeong Jin and Orlik, Philip V.},
- title = {{Millimeter Wave Communications Channel Estimation via Bayesian Group Sparse Recovery}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {3406--3410},
- month = mar,
- doi = {10.1109/ICASSP.2016.7472309},
- url = {https://www.merl.com/publications/TR2016-012}
- }